{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T01:27:26Z","timestamp":1794965246601,"version":"4.9.1"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,11,30]]},"abstract":"<jats:p>\n                    Recent approaches to congestion prediction and routability-driven placement have made progress, yet important limitations remain. Most existing models rely on heuristic-based intermediate features (e.g., RUDY, pin density) rather than fully end-to-end learning, and many capture either netlist topology or geometric placement context, but not both, limiting their performance. Moreover, when model gradients are used to guide placers, they are often propagated through such intermediate features, reducing their accuracy and effectiveness. To address these gaps, we propose\n                    <jats:monospace>TopoGeoNet<\/jats:monospace>\n                    , a heterogeneous neural network that unifies graph-based message passing with convolutional U-Net processing over spatial grids. Through bi-directional node\u2013grid communication,\n                    <jats:monospace>TopoGeoNet<\/jats:monospace>\n                    jointly leverages netlist topology and geometric placement information for accurate congestion prediction. Trained on ISPD\u20192016 FPGA benchmarks,\n                    <jats:monospace>TopoGeoNet<\/jats:monospace>\n                    achieves an 8.3% improvement in prediction accuracy over state-of-the-art ML baselines. When integrated into a routability-driven FPGA placer, it improves congestion scores by 16% on average and reduces total place-and-route runtime by 5% without degrading routed wirelength. Compared with state-of-the-art ML prediction models that provide inference and gradients through intermediate features,\n                    <jats:monospace>TopoGeoNet<\/jats:monospace>\n                    delivers superior routability results, highlighting the advantages of fully end-to-end prediction and differentiability.\n                  <\/jats:p>","DOI":"10.1145\/3808232","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:55:21Z","timestamp":1775818521000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["TopoGeoNet: A Heterogeneous Model for End-to-End Congestion Prediction and Optimization in FPGA Placement"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2249-841X","authenticated-orcid":false,"given":"Zhili","family":"Xiong","sequence":"first","affiliation":[{"name":"The University of Texas at Austin","place":["Austin, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0198-3462","authenticated-orcid":false,"given":"Zhishang","family":"Luo","sequence":"additional","affiliation":[{"name":"University of California San Diego","place":["San Diego, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6383-9709","authenticated-orcid":false,"given":"Rachel","family":"Rajarathnam","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin","place":["Austin, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7950-4348","authenticated-orcid":false,"given":"Yusu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California San Diego","place":["San Diego, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5705-2501","authenticated-orcid":false,"given":"David","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin","place":["Austin, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3233244"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045178"},{"key":"e_1_3_1_4_2","unstructured":"AMD. 2021. UltraScale Architecture. Retrieved February 1 2026 from https:\/\/www.xilinx.com\/products\/technology\/ultrascale.html"},{"key":"e_1_3_1_5_2","unstructured":"AMD. 2023. AMD-Xilinx Vivado ML Edition \u2013 2023.2. Retrieved February 1 2026 from https:\/\/www.xilinx.com\/support\/download\/index.html\/content\/xilinx\/en\/downloadNav\/vivado-design-tools\/archive.html"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63465-7_226"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3287970"},{"issue":"10","key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1109\/TCAD.2017.2778058","article-title":"RippleFPGA: Routability-driven simultaneous packing and placement for modern FPGAs","volume":"37","author":"Chen Gengjie","year":"2018","unstructured":"Gengjie Chen, Chak-Wa Pui, Wing-Kai Chow, Ka-Chun Lam, Jian Kuang, Evangeline F. Y. Young, and Bei Yu. 2018. RippleFPGA: Routability-driven simultaneous packing and placement for modern FPGAs. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 37, 10 (2018), 2022\u20132035.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415662"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2008.923063"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2859220"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643446"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671895"},{"key":"e_1_3_1_14_2","unstructured":"IEEE\/ACM MLCAD. 2023. MLCAD 2023 FPGA Macro-Placement Contest. Retrieved February 1 2026 from https:\/\/github.com\/TILOS-AI-Institute\/MLCAD-2023-FPGA-Macro-Placement-Contest"},{"key":"e_1_3_1_15_2","unstructured":"ISPD\u20192016 Contest. 2016. Xilinx Vivado v2015.4 (ISPD 2016 Contest Flow). Retrieved February 1 2026 from https:\/\/www.ispd.cc\/contests\/16\/Flow.txt"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2005.1560188"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/266021.266099"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2729349"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942075"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372780.3375560"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9473959"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2699873"},{"key":"e_1_3_1_23_2","series-title":"Proceedings of Machine Learning Research","first-page":"4258","volume-title":"Proceedings of the 27th International Conference on Artificial Intelligence and Statistics","volume":"238","author":"Luo Zhishang","year":"2024","unstructured":"Zhishang Luo, Truong Son Hy, Puoya Tabaghi, Micha\u00ebl Defferrard, Elahe Rezaei, Ryan M. Carey, Rhett Davis, Rajeev Jain, and Yusu Wang. 2024. DE-HNN: An effective neural model for Circuit Netlist representation. In Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, Sanjoy Dasgupta, Stephan Mandt, and Yingzhen Li (Eds.). Proceedings of Machine Learning Research, Vol. 238, PMLR, 4258\u20134266. Retrieved from https:\/\/proceedings.mlr.press\/v238\/luo24a.html"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00079"},{"key":"e_1_3_1_25_2","first-page":"281","volume-title":"Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability","volume":"1","author":"MacQueen J. B.","year":"1967","unstructured":"J. B. MacQueen. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1. University of California Press, Berkeley, CA, USA, 281\u2013297."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3698196"},{"key":"e_1_3_1_27_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Pei Hongbin","year":"2020","unstructured":"Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, and Bo Yang. 2020. Geom-GCN: Geometric graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR). Retrieved from https:\/\/openreview.net\/forum?id=S1e2agrFvS"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203880"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712562"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_1_31_2","series-title":"Proceedings of Machine Learning Research","first-page":"9323","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Satorras V\u00edctor Garcia","year":"2021","unstructured":"V\u00edctor Garcia Satorras, Emiel Hoogeboom, and Max Welling. 2021. E(n) equivariant graph neural networks. In Proceedings of the 38th International Conference on Machine Learning, Marina Meila and Tong Zhang (Eds.). Proceedings of Machine Learning Research, Vol. 139, PMLR, 9323\u20139332. Retrieved from https:\/\/proceedings.mlr.press\/v139\/satorras21a.html"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD55463.2022.9900091"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2007.364463"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3195975"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530675"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240843"},{"key":"e_1_3_1_38_2","unstructured":"AMD. 2026. UltraScale architecture and product data sheet: Overview (DS890). Rev 4 9 (2026). Retrieved February 1 2026 from https:\/\/docs.amd.com\/v\/u\/en-US\/ds890-ultrascale-overview"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2872334.2886419"},{"key":"e_1_3_1_40_2","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","volume":"35","author":"Yang Shang","year":"2022","unstructured":"Shang Yang, Zhe Yang, Dong Li, Yingxue Zhang, Zhenyu Zhang, Guojie Song, and Jianye Hao. 2022. Versatile multi-stage graph neural network for circuit representation. In Proceedings of the 36th International Conference on Neural Information Processing Systems, Vol. 35. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/7fa548155f40c014372146be387c4f6a-Abstract-Conference.html"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1231956.1231963"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317876"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T13:09:57Z","timestamp":1781528997000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11,30]]}},"alternative-id":["10.1145\/3808232"],"URL":"https:\/\/doi.org\/10.1145\/3808232","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2025-12-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}